{"total":19,"rows":[{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183,"area":null},{"id":"2505.02222","title":"Practical Efficiency of Muon for Pretraining","created":"2025-05-04","cited_by_count":80,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2306.17759","title":"The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit","created":"2023-06-30","cited_by_count":47,"area":null},{"id":"2406.09405","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","created":"2024-06-13","cited_by_count":46,"area":null},{"id":"2405.15712","title":"Infinite Limits of Multi-head Transformer Dynamics","created":"2024-05-24","cited_by_count":39,"area":null},{"id":"2403.02579","title":"Geometric Dynamics of Signal Propagation Predict Trainability of Transformers","created":"2024-03-05","cited_by_count":24,"area":null},{"id":"2307.03223","title":"Neural Network Field Theories: Non-Gaussianity, Actions, and Locality","created":"2023-07-06","cited_by_count":22,"area":null},{"id":"2505.24333","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","created":"2025-05-30","cited_by_count":17,"area":null},{"id":"2312.12226","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width","created":"2023-12-19","cited_by_count":15,"area":null},{"id":"2305.02334","title":"Structures of Neural Network Effective Theories","created":"2023-05-03","cited_by_count":13,"area":null},{"id":"2511.16741","title":"Fermions and Supersymmetry in Neural Network Field Theories","created":"2025-11-20","cited_by_count":6,"area":null},{"id":"2310.07765","title":"Feature Learning and Generalization in Deep Networks with Orthogonal Weights","created":"2023-10-11","cited_by_count":5,"area":null},{"id":"2506.00846","title":"Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2402.17440","title":"Principled Architecture-aware Scaling of Hyperparameters","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2306.11668","title":"Principles for Initialization and Architecture Selection in Graph Neural Networks with ReLU Activations","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2507.08963","title":"Stochastic Approximation with Block Coordinate Optimal Stepsizes","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2610.10033","title":"Gaussian Equivalence for Multi-Head Self-Attention","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}